RESUMEN
It is of great significance to identify the pest species accurately and control it effectively to reduce the loss of agricultural products. The research results of this project will provide theoretical basis for preventing and controlling the spread of pests and reducing the loss of agricultural products, and have important practical significance for improving the quality of agricultural products and increasing the output of agricultural products. At the same time, it provides a kind of effective prevention and control measures for farmers, so as to ensure the safety and health of crops. Because of the slow speed and high cost of manual identification, it is necessary to establish a set of automatic pest identification system. The traditional image-based insect classifier is mainly realized by machine vision technology, but because of its high complexity, the classification efficiency is low and it is difficult to meet the needs of applications. Therefore, it is necessary to develop a new automatic insect recognition system to improve the accuracy of insect classification. There are many species and forms of insects, and the field living environment is complex. The morphological similarity between species is high, which brings difficulties to the classification of insects. In recent years, with the rapid development of deep learning technology, using artificial neural network to classify pests is an important method to establish a fast and accurate classification model. In this work, we propose a novel convolutional neural network-based model (MSSN), which includes attention mechanism, feature pyramid, and fine-grained model. The model has good scalability, can better capture the semantic information in the image, and achieve more accurate classification. We evaluated our approach on a common data set: large-scale pest data set, PlantVillage benchmark data set, and evaluated model performance using a variety of evaluation indicators, namely, macro mean accuracy (MPre), macro mean recall rate (MRec), macro mean F1-score (MF1), Accuracy (Acc) and geometric mean (GM). Experimental results show that the proposed algorithm has better performance and universality ability than the existing algorithm. For example, on the data set, the maximum accuracy we obtained was 86.35%, which exceeded the corresponding technical level. The ablation experiment was conducted on the experiment itself, and the comprehensive evaluation of the complete MSSN(scale 1+2+3) was the best in various performance indexes, demonstrating the feasibility of the innovative method in this paper.
Asunto(s)
Agricultura , Redes Neurales de la Computación , Animales , Algoritmos , Productos Agrícolas , Difusión de la Información , InsectosRESUMEN
Objective:To investigate the predictive value of preoperative lymphocyte-to-monocyte ratio (LMR) combined with platelet-to-lymphocyte ratio (PLR) (LMR-PLR) scoring model for prognosis of pancreatic ductal adenocarcinoma (PDAC) after radical resection.Methods:The retrospective cohort study was conducted. The clinicopathological data of 116 patients with PDAC who were admitted to the Second Hospital of Lanzhou University from January 2015 to December 2019 were collected. There were 73 males and 43 females, aged 61.5(range, 29.0-75.0)years. All patients underwent radical resection for PDAC. Observation indicators: (1) optimal cut-off value of LMR and PLR; (2) clinicopathological features of patients with different scores of preoperative LMR-PLR scoring model; (3) follow-up and survival; (4) influencing factors for prognosis of PDAC patients; (5) construction and verification of nomogram prediction model. Measurement data with skewed distribution were represented as M(range). Count data were described as absolute numbers, and comparison between groups was conducted using the chi-square test. Comparison of ordinal data was conducted using the Mann-Whitney U test. The Graphpad prism 8 was used to draw survival curve, the Kaplan-Meier method was used to calculate survival rate, and the Log-Rank test was used for survival analysis. The COX proportional hazard regression model was used for univariate and multivariate analyses. The X-tile software was used to determine the optimal cut-off values of LMR and PLR. The nomogram prediction model was conducted based on the results of multivariate analysis, and the receiver operating characteristic (ROC) curve was drawn. The area under curve (AUC) was used to evaluate the discrimination of nomogram prediction model. The calibration curve was used to evaluate the consistency of nomogram prediction model and the decision curve was used to evaluate the clinical benefits. Results:(1) Optimal cut-off value of LMR and PLR. The optimal cut-off values of LMR and PLR were 1.9 and 156.3. (2) Clinicopathological features of patients with different scores of preoperative LMR-PLR scoring model. Cases with LMR-PLR scoring as 0, 1, 2 were 11, 42, 63. Cases with CA125 <12.4 U/mL, cases postoperative with vascular invasion, cases with postoperative chemotherapy in patients with 0, 1, 2 of LMR-PLR scoring were 1, 8, 24, 9, 27, 27, 3, 26, 43, showing significant differences among them ( χ2=6.73, 8.37, 6.68, P<0.05). (3) Follow-up and survival. All 116 patients were followed up for 39(range, 2-86)months. The 1-, 2-, 3-year survival rate of 116 PDAC patients was 50.9%, 37.9%, 19.3%, respectively, with a survival time of 13(range, 1-85)months. The survival time of patients with LMR-PLR scoring as 0, 1, 2 was 3(range, 1-9)months, 7(range, 2-56)months, 26(range, 2-85)months, respectively, showing a significant difference among them ( χ2=48.78, P<0.05). (4) Influencing factors for prognosis of PDAC patients. Results of multivariate analysis showed that carcinoembryonic antigen (CEA), CA19-9, LMR-PLR score, tumor diameter were independent factors affecting prognosis of patients ( hazard ratio=1.61, 1.88, 0.27, 1.87, 95% confidence interval as 1.02-2.54, 1.18-3.00, 0.19-0.39, 1.13-3.09, P<0.05). (5) Construction and verification of nomogram prediction model. The nomogram prediction model was constructed based on CEA, CA19-9, LMR-PLR score and tumor diameter. The AUC of ROC curve in predicting 1-, 2-, 3-year survival rate of patients was 0.86 (95% confidence interval as 0.79-0.93, P<0.05), 0.86 (95% confidence interval as 0.79-0.92, P<0.05), 0.87 (95% confidence interval as 0.78-0.95, P<0.05), respectively. Results of calibration curve showed that the predicted survival rate of nomogram prediction model was consistent with the actual survival rate, with the consistency index as 0.74. Results of decision curve showed that the predictive performance of nomogram prediction model was superior to that of a single factor at a risk threshold of 0.12-0.85. Conclusions:CEA, CA19-9, LMR-PLR score, tumor diameter are independent factors affecting prognosis of patients undergoing radical resection for PDAC, and the nomogram prediction model can predict postoperative survival rate. The predicted survival rate of nomogram prediction model is consistent with the actual survival rate, and the predictive performance of nomogram prediction model is superior to that of a single factor at a risk threshold of 0.12-0.85.
RESUMEN
External beam radiotherapy (EBRT) is one of the important treatment of thyroid cancer. EBRT is still controversial in some aspects of differentiated thyroid cancer. With the development of radiotherapy technology, improvement of equipment and accuracy, treatment complications caused by EBRT are significantly reduced. As a result, EBRT is valued again in the treatment of thyroid cancer, and its indications have been broadened. How to improve the curative effect and guarantee the quality of life becomes the focus of attention. EBRT may be an effective treatment for specific stage and pathological type of thyroid cancer. The multidisciplinary approach is expected to benefit more patients in the future.
RESUMEN
External beam radiotherapy (EBRT)is one of the important treatment of thyroid cancer. EBRT is still controversial in some aspects of differentiated thyroid cancer. With the development of radiothera-py technology,improvement of equipment and accuracy,treatment complications caused by EBRT are signifi-cantly reduced. As a result,EBRT is valued again in the treatment of thyroid cancer,and its indications have been broadened. How to improve the curative effect and guarantee the quality of life becomes the focus of atten-tion. EBRT may be an effective treatment for specific stage and pathological type of thyroid cancer. The multi-disciplinary approach is expected to benefit more patients in the future.
RESUMEN
Objective To investigate the clinical value of digital subtraction angiography (DSA) interventional thrombolysis in the treatment of acute cerebral infarction.Methods 35 patients with acute cerebral infarction were divided into 6h group and 7-12h group in accordance with DSA from the onset time.Before and after thrombolytic therapy,the nerve function defect angiographic recanalization rate and postoperative score of therapeutic effect evaluation were compared between the two groups.Results In the 6h group,the recanalization rate > 70% (33.33 %) and the recanalization rate >50% (83.33%) were significantly higher than those in the 7-12h group (18.18%,55.55%),and the differences were statistically significant(x2 =6.56,5.02,all P < 0.05).Before treatment,the ESS score between the two groups was not statistically significantly different(t =0.83,P > 0.05).After treatment for 1d,7d,14d,ESS scores of the two groups [(62.44 ± 9.82) points,(68.95 ± 11.23) points,(73.89 ± 11.24) points,(54.67 ± 9.11) points,(58.02 ± 10.47) points,(61.43 ± 10.23) points] were significantly higher than those before treatment [(42.12 ± 8.79) points,(41.92 ± 9.02) points,t =6.87,7.03,7.92,6.03,6.56,6.77,all P < 0.05].After treatment for 1 d,7d,14d,the ESS scores of the 6h group [(62.44 ± 9.82) points,(68.95 ± 11.23) points,(73.89 ± 11.24) points] were significantly higher than those of the 7-12h group [(54.67 ± 9.11) points,(58.02 ±10.47) points,(61.43 ± 10.23) points],and the differences were statistically significant(t =5.45,5.10,4.23,all P < 0.05).Conclusion DSA interventional thrombolytic therapy can significantly improve the neurological status of the patients,and the onset time is shorter.The clinical treatment is better.In the clinical treatment,we should grasp the opportunity.
RESUMEN
Objective@#To study the clinical results of Coflex and lumbar posterior decompression and fusion in the treatment of lumbar degenerative spondylolisthesis at L4-5.@*Methods@#Thirty-eight patients with Grade Ⅰ degenerative spondylolisthesis, from January 2008 to December 2011 in Beijing Chaoyang Hospital, Capital Medical University were reviewed, and patients were divided into two groups by randomness. Group A was treated with Coflex and group B with pedicle instrumentation and interbody fusion. Fifteen patients were included in group A, and 23 patients were included in group B. In group A, the average age was (56.3±9.1) years. In group B, the average age was (58.2±11.2) years. The clinical results were evaluated by visual analogue scale (VAS) and Oswestry disability index (ODI). Slip distance (SD) was measured before and after surgery, and the changes of intervertebral angle at index level and adjacent level were also recorded.@*Results@#The follow-up period was 36 to 68 months, with the average of (39±14) months in the both groups. The operation time and bleeding volume of patients in group A were significantly less than that of group B (P<0.05). In both groups, the difference of ODI and VAS before operation and postoperative follow-up were statistically significant (P<0.05). There was no significant difference between lumbar intervertebral angle and the sliding distance in group A at all time points. In the group B, there was a significant increase in the intervertebral angle and the sliding distance at L3-4 and L5-S1 level after surgery, the difference at upper and below adjacent segment before and after surgery were statistically significant.@*Conclusions@#Coflex interspinous dynamic stabilization system has same excellent clinical results as pedicle screw instrumentation and fusion surgery for the treatment of L4-5 degenerative spondylolisthesis; no significant progression of spondylolisthesis been observed during more than 3 years follow-up, and no obvious adjacent segment degeneration has been found.
RESUMEN
To observe the changes of intelligence in cerebral infarction patients, and to explore the relationship between intelligence and brain CT feature. Methods:The intelligence was measured by WAIS-RC in 80 cerebral infarction patients.Results:The VIQ and FIQ reduced significantly in the patients with hypertension. FIQ in patients with diabetes mellitus and PIQ in patients with cerebral vesscular disease histories reduced significantly. The PIQ reduced significantly in the patients of right focus on CT. VIQ, PIQ and FIQ reduced significantly in patients of cerebral cortices involved. But the number of focus, thalamus involved and cerebral atrophy were of no significance.Conclusion:The intelligence of the cerebral infarction patients companying hypertension, diabetes mellitus and several cerebral vesscular disease histories was impaired significantly. Cerebral cortices involed was the most important factor among the features on CT relating to intelligence quotient.
RESUMEN
Water and salt requirements were studied in 17 and 18 healthy young men respectively. Each subject walked in a hot and humid environment (DB 28-34℃, RH 50-76%) at a speed of 5 km/hr with backpack loads of 15-25 kg for four hours. Dehydration would occur if no water or inadequate water was supplied and it would affect circulatory, sweating and thermore-gulatory function. It was suggested that MCHC= mightbeasensitive index to determine whether the body was dehydrated or not and to evaluate adequate amount of drinking water. The results showed that water loss should be replaced preferably by periodic intake of small amounts of water throughout the work period and the total amount required was about 80% of sweat loss. Thus, the rise of body temperature and heart rate was less than that of the subjects drinking 250 ml/hr of water or drinking voluntarily and there was little change in MCHC. The results also showed that the loss of salt by sweating was closely related to heat acclimatization. Therefore it is imporatnt to provide adequate salt to those unacclima-tized. Those taking 20 gm/day had a mild increase of rectal temperature and heart rate during work period and their urinary excretions of chloride were above 5 gm/day. According to the experiment, 20 gm/day of salt gave a satisfactory result.
RESUMEN
Eight adult dogs distributed equally into control and therapy groups were fed on stock diet for 20 days and then irradiated whole-bodily with 60Co 4.65 Gy. After irradiation the control group was not given any therapeutic measure but fed on the diet as usual, while the therapy group was given with a larger amount of vitamins and high-caloric and high-protein diet, and sometimes force feeding was taken if the latter showed sign of anorexia. Whether higher values of nonprotein nitrogen in serum of two dogs in restored period and diarrhea happened in the therapy group were attribute to The treatments such as high-protein diet and force feeding were still unknown, the curing effects of nutrition and antibiotics were distinct as shown in that the body weight was easily maintained, and that the anemia and leucopenia wereless severe and recovered early. Moreover, within 30 days both the ther apy andcontrol groups one dog died respectively but survival time of the former was longer than the latter.